You can deploy this model and start earning money today!

hfunknown/
qwen3-8b-knapsack-lora-persistent-seed777

Name: qwen3-8b-knapsack-lora-persistent-seed777
Availability: InStock

Views

No views yet

qwen3-8b-knapsack-lora-persistent-seed777

Anonymous supplementary release for a double-blind workshop submission. This is one of six LoRA adapters (persistent/stateless training regime x 3 seeds) fine-tuned on the Opaque Knapsack agentic task.

Base model: Qwen/Qwen3-8B
Training regime: persistent (trained with a persistent Python interpreter runtime (state carries over across agent turns))
Seed: 777

Training configuration

Fine-tuned with Axolotl 0.13.2, LoRA adapter, 4-bit NF4 quantized base:

Hyperparameter	Value
lora_r	64
lora_alpha	128
lora_dropout	0.05
lora_target_modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
learning_rate	1e-4
lr_scheduler	cosine
optimizer	adamw_torch
epochs	3.0
micro_batch_size	1
gradient_accumulation_steps	16
sequence_len	16384
sample_packing	false
seed	777
training data	paired traces for the "persistent" regime (see paper Appendix for pairing/filtering procedure)

Provenance

Released anonymously alongside a NeurIPS workshop submission for reproducibility review. Non-anonymous release (paper citation, full code, full training traces) will follow after the review process concludes.

hfunknown/qwen3-8b-knapsack-lora-persistent-seed777

qwen3-8b-knapsack-lora-persistent-seed777

Training configuration

Provenance

hfunknown/
qwen3-8b-knapsack-lora-persistent-seed777